© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26500
    Prev
    Next
    INDEX
    Explanations

    regions and areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĪ¶
    -0.08
    åį¯
    -0.08
     Moran
    -0.08
    (flow
    -0.08
    为ä¼ģä¸ļ
    -0.08
    æĺ
    -0.08
     moz
    -0.08
    涣
    -0.08
     Walter
    -0.08
     afr
    -0.08
    POSITIVE LOGITS
     region
    0.12
    èµĽåĮº
    0.11
    举åĮĹ
    0.11
    åĮºåŁŁåĨħ
    0.11
    åĮºåŁŁ
    0.10
    èħ¹
    0.10
     Region
    0.10
    åįĢåŁŁ
    0.10
    åĪĨåĮº
    0.09
    REGION
    0.09
    Activations Density 0.228%

    No Known Activations